Compare model prices
Input, output, cached and batch prices, every route and a month of tokens, side by side.
A month of tokens
Qwen3.5-27B$50.70
Qwen3.8 Max Prime$640.00
100M input and 20M output tokens, list price. Use your own numbers.
Side by side
| Qwen3.5-27B | Qwen3.8 Max Prime | |
|---|---|---|
| Input per 1M | $0.195 | $4 |
| Output per 1M | $1.56 | $12 |
| Cached input | n/a | $0.5 |
| Batch in / out | n/a | n/a |
| Blended (3:1) | $0.536 | $6 |
| Context | 262K | 1M |
| Routes | 6 | 1 |
| Released | Feb 25, 2026 | Sep 23, 2026 |
| Leadersboard score | n/a | n/a |
On the price map
Size: context window, 8K to 2MEqual blended cost (3:1) 243 models, lower left is cheaper
Every route
Qwen3.5-27B
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
The lab's own API | $0.195 | $1.56 | $0.195 / $1.56List price | n/a | List price |
fp8 | $0.25 | $2 | $0.25 / $2+28% vs list | n/a | +28% vs list |
| AtlasCloud fp8 · cached $0.27 | $0.27 | $2.16 | $0.27 / $2.16+38% vs list | $0.27 | +38% vs list |
bf16 | $0.3 | $2.4 | $0.3 / $2.4+54% vs list | n/a | +54% vs list |
| Phala Default region · cached $0.15 | $0.3 | $2.4 | $0.3 / $2.4+54% vs list | $0.15 | +54% vs list |
fp8 | $0.26 | $2.6 | $0.26 / $2.6+58% vs list | n/a | +58% vs list |
Qwen3.8 Max Prime
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
The lab's own API · cached $0.5 | $4 | $12 | $4 / $12List price | $0.5 | List price |
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.